> > Aaron wrote: > Autoencoders, PCA, and their close relatives are the only methods to date > which even *attempt *to solve this problem, to my knowledge. These two > families of algorithms are specifically engineered to the task of > identifying features without supervision. Both are data intensive, and I > think this is probably intrinsic to the task itself. Either you have to > know in advance how to recognize relevant features, or you have to learn > from experience. >
Perhaps you my find Perlovsky's work on dynamic logic<http://en.wikipedia.org/wiki/Dynamic_logic_(neural)#Dynamic_logic_.28neural.29> relevant to some of these concerns. Most of the dynamic logic basics are laid out in an open access article Grounded Symbols In The Brain, Computational Foundations For Perceptual Symbol System<http://www.webmedcentral.com/article_view/1357>. Whereas the paper discusses mostiy lower levels of cognition, he addresses the concept of situational awareness, context understanding and planning more deeply in his text Emotional Cognitive Neural Algorithms with Engineering Applications: Dynamic Logic: From Vague to Crisp<http://www.amazon.com/Emotional-Cognitive-Algorithms-Engineering-Applications/dp/3642228291/ref=la_B001H6OSEU_1_3?s=books&ie=UTF8&qid=1388553921&sr=1-3> ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
